Robust automatic brain vessel segmentation in 3D CTA scans using dynamic 4D-CTA data

2026-01-30

AI Summary

This study addresses the challenges of automatic cerebrovascular segmentation in 3D CTA—namely, sensitivity to contrast agent timing, high annotation costs, and limited robustness—by leveraging dynamic 4D-CTA multi-phase data for the first time. The authors enhance vascular visualization through bone and soft tissue subtraction and reuse a single high-quality annotation across multiple phases, substantially expanding the training set. This strategy significantly reduces manual annotation effort while improving model generalization across varying contrast phases. Built upon nnUNet, the proposed segmentation model achieves state-of-the-art performance on the TopBrain test set, with mean Dice scores of 0.846 for arteries and 0.957 for veins, mean directed Hausdorff distances as low as 0.304 mm and 0.078 mm, and topological sensitivities of 0.877 and 0.974, respectively, markedly outperforming existing methods.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

In this study, we develop a novel methodology for annotating the brain vasculature using dynamic 4D-CTA head scans. By using multiple time points from dynamic CTA acquisitions, we subtract bone and soft tissue to enhance the visualization of arteries and veins, reducing the effort required to obtain manual annotations of brain vessels. We then train deep learning models on our ground truth annotations by using the same segmentation for multiple phases from the dynamic 4D-CTA collection, effectively enlarging our dataset by 4 to 5 times and inducing robustness to contrast phases. In total, our dataset comprises 110 training images from 25 patients and 165 test images from 14 patients. In comparison with two similarly-sized datasets for CTA-based brain vessel segmentation, a nnUNet model trained on our dataset can achieve significantly better segmentations across all vascular regions, with an average mDC of 0.846 for arteries and 0.957 for veins in the TopBrain dataset. Furthermore, metrics such as average directed Hausdorff distance (adHD) and topology sensitivity (tSens) reflected similar trends: using our dataset resulted in low error margins (adHD of 0.304 mm for arteries and 0.078 for veins) and high sensitivity (tSens of 0.877 for arteries and 0.974 for veins), indicating excellent accuracy in capturing vessel morphology. Our code and model weights are available online at https://github.com/alceballosa/robust-vessel-segmentation

Problem

• brain vessel segmentation
• 3D CTA
• dynamic 4D-CTA
• automatic segmentation
• vascular morphology

Innovation

• 4D-CTA
• dynamic subtraction
• vessel segmentation
• data augmentation
• contrast-phase robustness